Rémi Pautrat

UPAL achieves a remarkable 4x speedup and 10x smaller memory footprint while maintaining state-of-the-art performance in multi-view feature extraction.

Jointly optimizing multi-room layouts as Manhattan polygons leads to significant gains in accuracy and robustness, outperforming traditional independent room estimation methods.

Video Language Models can achieve up to 86% faster time-to-first-token and 93% token reduction by ditching full-image encoding in favor of motion vectors and residuals from video codecs.